Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 315 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8276. Min Range: -1.8276

Max Act: 1.8276. Min Act: -0.0000

Data Index: 1499175 (Python Code)

Max Activating Token Index: 340

Text #1

Max Range: 1.8276. Min Range: -1.8276

Max Act: 1.7727. Min Act: -0.0000

Data Index: 1472778 (Python Code)

Max Activating Token Index: 545

Text #2

Max Range: 1.8276. Min Range: -1.8276

Max Act: 1.6776. Min Act: -0.0000

Data Index: 1503401 (Python Code)

Max Activating Token Index: 854

Text #3

Max Range: 1.8276. Min Range: -1.8276

Max Act: 1.7108. Min Act: -0.0000

Data Index: 1567981 (Python Code)

Max Activating Token Index: 41

Text #4

Max Range: 1.8276. Min Range: -1.8276

Max Act: 1.7092. Min Act: -0.0000

Data Index: 1650799 (Python Code)

Max Activating Token Index: 72

Text #5

Max Range: 1.8276. Min Range: -1.8276

Max Act: 1.6926. Min Act: -0.0000

Data Index: 1424018 (Python Code)

Max Activating Token Index: 88

Text #6

Max Range: 1.8276. Min Range: -1.8276

Max Act: 1.6939. Min Act: -0.0000

Data Index: 1427107 (Python Code)

Max Activating Token Index: 823

Text #7

Max Range: 1.8276. Min Range: -1.8276

Max Act: 1.5774. Min Act: -0.0000

Data Index: 1402162 (Python Code)

Max Activating Token Index: 197

Text #8

Max Range: 1.8276. Min Range: -1.8276

Max Act: 1.6528. Min Act: -0.0000

Data Index: 1479879 (Python Code)

Max Activating Token Index: 123

Text #9

Max Range: 1.8276. Min Range: -1.8276

Max Act: 1.6088. Min Act: -0.0000

Data Index: 1402220 (Python Code)

Max Activating Token Index: 189

Text #10

Max Range: 1.8276. Min Range: -1.8276

Max Act: 1.5514. Min Act: -0.0000

Data Index: 1444835 (Python Code)

Max Activating Token Index: 70

Text #11

Max Range: 1.8276. Min Range: -1.8276

Max Act: 1.5289. Min Act: -0.0000

Data Index: 1590150 (Python Code)

Max Activating Token Index: 213

Text #12

Max Range: 1.8276. Min Range: -1.8276

Max Act: 1.6209. Min Act: -0.0000

Data Index: 1536526 (Python Code)

Max Activating Token Index: 45

Text #13

Max Range: 1.8276. Min Range: -1.8276

Max Act: 1.5839. Min Act: -0.0000

Data Index: 1407223 (Python Code)

Max Activating Token Index: 480

Text #14

Max Range: 1.8276. Min Range: -1.8276

Max Act: 1.6595. Min Act: -0.0000

Data Index: 1398666 (Python Code)

Max Activating Token Index: 196

Text #15

Max Range: 1.8276. Min Range: -1.8276

Max Act: 1.5031. Min Act: -0.0000

Data Index: 1590804 (Python Code)

Max Activating Token Index: 563

Text #16

Max Range: 1.8276. Min Range: -1.8276

Max Act: 1.4241. Min Act: -0.0000

Data Index: 1445863 (Python Code)

Max Activating Token Index: 134

Text #17

Max Range: 1.8276. Min Range: -1.8276

Max Act: 1.5131. Min Act: -0.0000

Data Index: 1498970 (Python Code)

Max Activating Token Index: 123

Text #18

Max Range: 1.8276. Min Range: -1.8276

Max Act: 1.5481. Min Act: -0.0000

Data Index: 1414913 (Python Code)

Max Activating Token Index: 814

Text #19

Max Range: 1.8276. Min Range: -1.8276

Max Act: 1.3678. Min Act: -0.0000

Data Index: 1494145 (Python Code)

Max Activating Token Index: 910